Crack Detection from Weld Bend Test Images Using R-CNN.

The personnel burden is an issue with the visual inspection of welding defects that occur in bend test fragments. This study aims to construct an automatic evaluation system for welding defects that occur in bend test fragments. This paper describes the automatic detection of defective areas from bend test fragments using R-CNN. First, we have described the structure of the proposed R-CNN, followed by the experiments for evaluating R-CNN and their results. Finally, we have provided a conclusion and discussed future issues.